[1]张礼雄,张忠林.视频中多目标车辆的检测与跟踪方法研究[J].计算机技术与发展,2018,28(07):125-129.[doi:10.3969/ j. issn.1673-629X.2018.07.027]
　ZHANG Li-xiong,ZHANG Zhong-lin.Research on Method of Detection and Tracking of Multi-objective Vehicle Based on Video[J].,2018,28(07):125-129.[doi:10.3969/ j. issn.1673-629X.2018.07.027]
点击复制

视频中多目标车辆的检测与跟踪方法研究()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
28
期数:
2018年07期
页码:
125-129
栏目:
应用开发研究
出版日期:
2018-07-10

文章信息/Info

Title:
Research on Method of Detection and Tracking of Multi-objective Vehicle Based on Video
文章编号:
1673-629X(2018)07-0125-05
作者:
张礼雄; 张忠林
兰州交通大学 电子与信息工程学院,甘肃 兰州 730070
Author(s):
ZHANG Li-xiong; ZHANG Zhong-lin
School of Electronic and Information Engineering,Lanzhou Jiaotong University,Lanzhou 730070,China
关键词:
车辆检测与追踪; Adaboost 算法; 帧差法; KCF 算法
Keywords:
vehicle detection and tracking; Adaboost; frame difference method; KCF
分类号:
TP301
DOI:
10.3969/ j. issn.1673-629X.2018.07.027
文献标志码:
A
摘要:
为了提高行驶车辆检测与追踪的准确性、时效性,提出了一个基于熵值法求权重的 Adaboost 和帧差法的混合检测模型。 首先对路面车道线进行识别与分割,将当前摄像头所在的路面作为感兴趣区域提取出来;然后对区域内的车辆使用该模型进行检测与定位;最后使用改进的 KCF 算法对检测到的车辆进行追踪。 实验结果证明,该方法可有效地滤除其他非目标物体,对车辆进行有效地筛选,准确率达 95.5%,且检测效率较高,适合在路面场景下对汽车进行有效的检测与追踪。 该模型优化了计算资源的使用数量,并且保证了在大量的图像帧中快速地识别与追踪车辆。
Abstract:
In order to improve the accuracy and timeliness of the moving vehicles’ detection and tracking,we propose a hybrid detection model based on Adaboost of obtaining weight by entropy method and frame difference. Firstly,we identify and segment the road lanes,taking the road where the camera is located in as the region of interest. Then the model is used to detect and locate the vehicles of the region. Finally the detected vehicles are tracked by the improved KCF algorithm. Experiment shows that this method can effectively filter out other non-target objects and screen the vehicles,and its accuracy can reach by 95.5 percent,which has high measuring efficiency and can be used to detect and track vehicles effectively in the road scene. It optimizes the usage quantity of computing resource,and guarantees the quick recognition and vehicle tracking in a large number of image frames.

相似文献/References:

[1]王 燕,曹建芳,李艳飞.融合混合优化组合的大规模场景图像分类算法[J].计算机技术与发展,2019,29(09):86.[doi:10. 3969 / j. issn. 1673-629X. 2019. 09. 017]
　WANG Yan,CAO Jian-fang,LI Yan-fei.A Classification Algorithm for Large-scale Scene Images Fusing Hybrid Optimization and Combination[J].,2019,29(07):86.[doi:10. 3969 / j. issn. 1673-629X. 2019. 09. 017]
[2]史双飞,张 震.基于决策的人脸检测与自动跟踪方法[J].计算机技术与发展,2019,29(09):35.[doi:10. 3969 / j. issn. 1673-629X. 2019. 09. 007]
　SHI Shuang-fei,ZHANG Zhen.A Method of Face Detection and Automatic Tracking Based on Decision Making[J].,2019,29(07):35.[doi:10. 3969 / j. issn. 1673-629X. 2019. 09. 007]
[3]乔旭坤,李 顺,李 君,等.基于机器学习的硬盘故障预测研究[J].计算机技术与发展,2022,32(06):215.[doi:10. 3969 / j. issn. 1673-629X. 2022. 06. 036]
　QIAO Xu-kun,LI Shun,LI Jun,et al.Research on Hard Disk Failure Prediction Based on Machine Learning[J].,2022,32(07):215.[doi:10. 3969 / j. issn. 1673-629X. 2022. 06. 036]

更新日期/Last Update: 2018-09-04